hf.co/TheDrummer/Cydonia-24B-v4.3-GGUF:Q4_K_M
OLLAMA GGUFllama · 23.6B · unknown
Oct 2, 2026 · Cortex-X925
qwen/qwen3-coder-30b
LM-STUDIO GGUFqwen3moe · 30B · Q4_K_M
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
Global Score
30 vs 85
Hardware Fit
48 vs 79
Quality Score
22 vs 88
Hardware
hf.co/TheDrummer/C… qwen/qwen3-coder-30b
MachineNVIDIA NVIDIA_DGX_SparkGMKtec EVO-X3
CPUCortex-X925AMD RYZEN AI MAX+ 395
Cores2032
RAM122 GB120 GB
GPUDevice 2e12AMD Radeon(TM) 8060S Graphics
OSUbuntu 24.04.5 LTSMicrosoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modeperformancebalanced
Performance
hf.co/TheDrummer/C… qwen/qwen3-coder-30b
Tokens/sec14.442.3
First chunk5450 ms10 ms
TTFT5.5 s707 ms
Load time22.7 s167.7 s
Memory usage18.5 GB70.3 GB
Memory %15%59%
HW Fit Score Breakdown
hf.co/TheDrummer/Cydoni…
Speed
14/50
TTFT
4/20
Memory
30/30
qwen/qwen3-coder-30b
Speed
40/50
TTFT
18/20
Memory
21/30
Quality
hf.co/TheDrummer/Cydoni…
Reasoning
16/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
6/15
Multilingual
0/10
Reasoning: Strong Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Poor
qwen/qwen3-coder-30b
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest